Predictive models that are composed of a number of combined models, although ubiquitous in climate prediction have not yet become popular in many other areas of environmental modelling, despite growing evidence that they are superior to single-model methods in many ways. These combined-model methodologies are termed ensembles and modules, and this paper reviews their concepts, advantages and how to create them. Additionally, they will be discussed in terms of the critically important bias/variance trade-off. Moreover, ensembles and modules will be discussed with reference to historical and current research papers within environmental modelling. (C) 2008 Elsevier B.V. All rights reserved.
展开▼
